{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T06:44:38Z","timestamp":1776753878352,"version":"3.51.2"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2016,5,30]],"date-time":"2016-05-30T00:00:00Z","timestamp":1464566400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2017,1]]},"DOI":"10.1007\/s11263-016-0913-6","type":"journal-article","created":{"date-parts":[[2016,5,30]],"date-time":"2016-05-30T05:44:34Z","timestamp":1464587074000},"page":"5-25","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Spatially Coherent Interpretations of Videos Using Pattern Theory"],"prefix":"10.1007","volume":"121","author":[{"given":"Fillipe D. M.","family":"de Souza","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sudeep","family":"Sarkar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anuj","family":"Srivastava","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingyong","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,5,30]]},"reference":[{"issue":"12","key":"913_CR1","doi-asserted-by":"crossref","first-page":"2246","DOI":"10.1109\/TPAMI.2010.33","volume":"32","author":"M Albanese","year":"2010","unstructured":"Albanese, M., Chellappa, R., Cuntoor, N., Moscato, V., Picariello, A., Subrahmanian, V., et al. (2010). Pads: A probabilistic activity detection framework for video data. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(12), 2246\u20132261.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"6","key":"913_CR2","doi-asserted-by":"crossref","first-page":"982","DOI":"10.1109\/TMM.2008.2001369","volume":"10","author":"M Albanese","year":"2008","unstructured":"Albanese, M., Chellappa, R., Moscato, V., Picariello, A., Subrahmanian, V., Turaga, P., et al. (2008). A constrained probabilistic petri net framework for human activity detection in video. IEEE Transactions on Multimedia, 10(6), 982\u2013996.","journal-title":"IEEE Transactions on Multimedia"},{"key":"913_CR3","doi-asserted-by":"crossref","unstructured":"Amer, M.R., Todorovic, S., Fern, A., Zhu, S.C. (2013). Monte carlo tree search for scheduling activity recognition. In IEEE International Conference on Computer Vision (ICCV) (pp. 1353\u20131360).","DOI":"10.1109\/ICCV.2013.171"},{"key":"913_CR4","doi-asserted-by":"crossref","unstructured":"Bhattacharya, S., Kalayeh, M.M., Sukthankar, R., Shah, M. (2014). Recognition of complex events: Exploiting temporal dynamics between underlying concepts. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","DOI":"10.1109\/CVPR.2014.287"},{"key":"913_CR5","doi-asserted-by":"crossref","unstructured":"Brendel, W., Fern, A., Todorovic, S. (2011). Probabilistic event logic for interval-based event recognition. In: CVPR.","DOI":"10.1109\/CVPR.2011.5995491"},{"issue":"3","key":"913_CR6","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1145\/1961189.1961199","volume":"2","author":"CC Chang","year":"2011","unstructured":"Chang, C. C., & Lin, C. J. (2011). Libsvm: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2(3), 27.","journal-title":"ACM Transactions on Intelligent Systems and Technology"},{"key":"913_CR7","unstructured":"Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P. (2011). Smote: Synthetic minority over-sampling technique. arXiv preprint arXiv:1106.1813 ."},{"key":"913_CR8","doi-asserted-by":"crossref","unstructured":"Das, P., Xu, C., Doell, R.F., Corso, J.J. (2013). A thousand frames in just a few words: Lingual description of videos through latent topics and sparse object stitching. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 2634\u20132641).","DOI":"10.1109\/CVPR.2013.340"},{"key":"913_CR9","unstructured":"de\u00a0Souza, F.D.M., Sarkar, S., Srivastava, A., Su, J. (2014). Pattern theory-based interpretation of activities. In: IEEE International Conference on Pattern Recognition (ICPR)."},{"key":"913_CR10","unstructured":"Dubba, K.S.R. (2012). Learning relational event models from videos. Ph.D. thesis, University of Leeds."},{"key":"913_CR11","doi-asserted-by":"crossref","unstructured":"Gan, C., Wang, N., Yang, Y., Yeung, D.Y., Hauptmann, A.G.: Devnet: A deep event network for multimedia event detection and evidence recounting. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015).","DOI":"10.1109\/CVPR.2015.7298872"},{"key":"913_CR12","doi-asserted-by":"crossref","unstructured":"Ghanem, N., DeMenthon, D., Doermann, D., Davis, L. (2004). Representation and recognition of events in surveillance video using petri nets. In: IEEE Conference on Computer Vision and Pattern Recognition Workshop. 2004. CVPRW\u201904 (pp. 112\u2013112).","DOI":"10.1109\/CVPR.2004.430"},{"key":"913_CR13","volume-title":"General pattern theory: A mathematical study of regular structures","author":"U Grenander","year":"1993","unstructured":"Grenander, U. (1993). General pattern theory: A mathematical study of regular structures. Oxford: Clarendon Press."},{"key":"913_CR14","volume-title":"Pattern theory: From representation to inference","author":"U Grenander","year":"2007","unstructured":"Grenander, U., & Miller, M. I. (2007). Pattern theory: From representation to inference (Vol. 1). Oxford: Oxford University Press."},{"key":"913_CR15","unstructured":"Hilde, K., Arslan, A., Serre, T. (2014). The language of actions: Recovering the syntax and semantics of goal-directed human activities. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"issue":"8","key":"913_CR16","doi-asserted-by":"crossref","first-page":"852","DOI":"10.1109\/34.868686","volume":"22","author":"YA Ivanov","year":"2000","unstructured":"Ivanov, Y. A., & Bobick, A. F. (2000). Recognition of visual activities and interactions by stochastic parsing. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 22(8), 852\u2013872.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"913_CR17","doi-asserted-by":"crossref","unstructured":"Jiang, Y.-G., Bhattacharya, S., Chang, S.-F., & Shah, M. (2013). High-level event recognition in unconstrained videos. International Journal of Multimedia Information Retrieval, 2(2), 73\u2013101.","DOI":"10.1007\/s13735-012-0024-2"},{"key":"913_CR18","doi-asserted-by":"crossref","unstructured":"Joo, S.W., Chellappa, R. (2006). Recognition of multi-object events using attribute grammars. In: IEEE International Conference on Image Processing (pp. 2897\u20132900).","DOI":"10.1109\/ICIP.2006.313035"},{"key":"913_CR19","doi-asserted-by":"crossref","unstructured":"Ke, Y., Sukthankar, R., Hebert, M. (2007). Event detection in crowded videos. In: ICCV.","DOI":"10.1109\/ICCV.2007.4409011"},{"key":"913_CR20","unstructured":"Lan, T., Sigal, L., Mori, G. (2012). Social roles in hierarchical models for human activity recognition. In: CVPR."},{"key":"913_CR21","doi-asserted-by":"crossref","unstructured":"Lan, T., Wang, Y., Yang, W., Robinovitch, S., & Mori, G. (2012). Discriminative latent models for recognizing contextual group activities. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(8), 1549\u20131562.","DOI":"10.1109\/TPAMI.2011.228"},{"key":"913_CR22","doi-asserted-by":"crossref","unstructured":"Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B. (2008). Learning realistic human actions from movies. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 1\u20138).","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"913_CR23","doi-asserted-by":"crossref","unstructured":"Morariu, V.I., Davis, L.S. (2011). Multi-agent event recognition in structured scenarios. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 3289\u20133296).","DOI":"10.1109\/CVPR.2011.5995386"},{"key":"913_CR24","unstructured":"Narayanaswamy, S., Barbu, A., Siskind, J. (2014). Seeing what you\u0155e told: Sentence-guided activity recognition in video. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"913_CR25","doi-asserted-by":"crossref","unstructured":"Pei, M., Jia, Y., Zhu, S.C. (2011). Parsing video events with goal inference and intent prediction. In: IEEE International Conference on Computer Vision (ICCV) (pp. 487\u2013494).","DOI":"10.1109\/ICCV.2011.6126279"},{"key":"913_CR26","doi-asserted-by":"crossref","unstructured":"Romdhane, R., Boulay, B., Bremond, F., Thonnat, M. (2011). Probabilistic recognition of complex event. In: Computer Vision Systems (CVS) (pp. 122\u2013131). Springer.","DOI":"10.1007\/978-3-642-23968-7_13"},{"key":"913_CR27","unstructured":"Ryoo, M.S., Aggarwal, J.K. (2007). Robust human-computer interaction system guiding a user by providing feedback. In: IJCAI (pp. 2850\u20132855)."},{"key":"913_CR28","doi-asserted-by":"crossref","unstructured":"Sadanand, S., Corso, J.J. (2012). Action bank: A high-level representation of activity in video. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.","DOI":"10.1109\/CVPR.2012.6247806"},{"key":"913_CR29","unstructured":"Shu, T., Xie, D., Rothrock, B., Todorovic, S., Zhu, S.C. (2015). Joint inference of groups, events and human roles in aerial videos. In: CVPR."},{"key":"913_CR30","doi-asserted-by":"crossref","unstructured":"Si, Z., Pei, M., Yao, B., Zhu, S.C. (2011). Unsupervised learning of event and-or grammar and semantics from video. In: IEEE International Conference on Computer Vision (ICCV) (pp. 41\u201348).","DOI":"10.1109\/ICCV.2011.6126223"},{"key":"913_CR31","doi-asserted-by":"crossref","unstructured":"Souza, F., Sarkar, S., Srivastava, A., Su, J. (2015). Temporally coherent interpretations for long videos using pattern theory. In: CVPR.","DOI":"10.1109\/CVPR.2015.7298727"},{"key":"913_CR32","unstructured":"Vahdat, A., Cannons, K., Mori, G., Kim, I., Oh, S. (2013). Compositional models for video event detection: A multiple kernel learning latent variable approach. In: ICCV."},{"key":"913_CR33","doi-asserted-by":"crossref","unstructured":"Wang, X., Ji, Q. (2015). Video event recognition with deep hierarchical context model. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","DOI":"10.1109\/CVPR.2015.7299071"},{"key":"913_CR34","unstructured":"Wei, P., Zhao, Y., Zheng, N., Zhu, S.C. (2013). Modeling 4d human-object interactions for event and object recognition. In: ICCV."},{"key":"913_CR35","doi-asserted-by":"crossref","unstructured":"Xu, Z., Yang, Y., Hauptmann, A.G. (2015). A discriminative cnn video representation for event detection. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","DOI":"10.1109\/CVPR.2015.7298789"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-016-0913-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-016-0913-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-016-0913-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-016-0913-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T12:19:20Z","timestamp":1559391560000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-016-0913-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,5,30]]},"references-count":35,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2017,1]]}},"alternative-id":["913"],"URL":"https:\/\/doi.org\/10.1007\/s11263-016-0913-6","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,5,30]]}}}